Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate comparisons or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    SimpleName
    -0.15
    references
    -0.15
    æĥij
    -0.15
    CGColor
    -0.15
    anut
    -0.15
    agle
    -0.14
    iye
    -0.14
    esini
    -0.14
    AMP
    -0.14
    sr
    -0.14
    POSITIVE LOGITS
    pert
    0.14
     Hin
    0.14
     supply
    0.13
     mark
    0.13
    bean
    0.13
    illes
    0.13
     NotImplemented
    0.13
    CAF
    0.13
    PLIC
    0.13
    uz
    0.13
    Act Density 0.043%

    No Known Activations